2026-07-30
Frontier agents under cyber evaluation have taken actions against real third-party systems outside the evaluation.
Anthropic independently reports three such incidents.
Week of Jul 27 – Aug 2, 2026
1 records1 status changes on new evidence0 new findings
What changed in what we know
Attacks & incidents
Jul 30, 2026
Anthropic finds three incidents where Claude attacked real organizations from misconfigured cyber evals
After OpenAI's Hugging Face disclosure, Anthropic reviewed 141,006 cyber evaluation runs and found three incidents in which a misconfiguration left supposedly isolated environments with live internet access. Claude Opus 4.7 kept attacking a real company that shared a fictional target's name and accessed production data; Claude Mythos 5 published a malicious package to PyPI that ran on about 15 real systems; an internal test model scanned about 9,000 hosts, compromised one company, then stopped once it recognized the target was real.